The Novel Method of Structural Health Monitoring Using FEM and Neural Networks

2005 ◽  
pp. 2099-2102
Author(s):  
Shijie Zheng ◽  
Hong Tao Wang ◽  
Lifeng Liu
Keyword(s):  
Neural Networks ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
The Novel ◽  
Structural Health ◽  
Novel Method

A Novel Method of Extracting Damage-Sensitive Feature for Electromechanical Impedance-Based Structural Health Monitoring

2011 ◽  
Vol 94-96 ◽  
pp. 1231-1234
Author(s):  
Xin Feng ◽  
Chun Yuan Zuo ◽  
Jing Zhou
Keyword(s):  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Piezoelectric Ceramic ◽  
The Novel ◽  
Electromechanical Impedance ◽  
Powerful Technique ◽  
Structural Health ◽  
Before And After ◽  
Novel Method

The electromechanical impedance (EMI) technique, which employs piezoelectric ceramic (PZT) patches as transducers, is emerging as an effective and powerful technique in structural health monitoring (SHM). This paper presents a novel method to extract the damage-sensitive feature (DSF) for EMI-based SHM. Firstly, the concept of effective drive point (EDP) impedance was introduced briefly. Secondly, a novel DSF was proposed as the ratio of the active parts of EDP admittances before and after damages. Finally, the effectiveness of the proposed DSF was experimentally verified. The results show that the novel method provides a sensitive feature for EMI-based SHM

scholarly journals Optimisation of acoustic emission wavestreaming for structural health monitoring

2020 ◽  
Vol 19 (6) ◽  
pp. 2007-2022
Author(s):  
John P McCrory ◽  
Matthew R Pearson ◽  
Rhys Pullin ◽  
Karen M Holford
Keyword(s):  
Acoustic Emission ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Peak Frequency ◽  
Image Correlation ◽  
The Novel ◽  
Structural Health ◽  
Growth Activity ◽  
Materials Used ◽  
Novel Concept

Structural health monitoring has gained wide appeal for applications with high inspection costs, such as aircraft and wind turbines. As the structures and materials used in these industries evolve, so too must the technologies used to monitor them. Acoustic emission is a passive method of detecting damage which lends itself well to structural health monitoring. One form of acoustic emission monitoring, known as wavestreaming, involves intermittently recording data for set periods of time and using the sequential recordings to detect changes in the state of the structure. However, at present, there is no standard method for selecting appropriate wavestream recording parameters, such as their length or their interval of collection. This article investigates a method of optimising acoustic emission wavestreaming for structural health monitoring purposes by introducing the novel concept of adjoining consecutive discrete acoustic emission hit signals to create synthetic wavestreams. To this end, a pre-notched 492 mm × 67.5 mm × 20 mm, 300M grade steel cantilever specimen was subject to cyclic loading and both acoustic emission hit data and conventional wavestreams were collected as a crack grew in the notched region; crack growth activity was also monitored using digital image correlation for comparison. To demonstrate the proposed optimisation process, four sets of synthetic wavestreams were created from the hit data, 0.25, 0.5, 1.0 and 1.5 s in length, and compared with the 1.5-s-long conventional wavestreams. The activity of the peak frequency and frequency centroid bands of interest within the conventional and synthetic wavestreams were examined to determine whether or not cracking activity could be inferred through them. Across comparisons of all data, it was found that the 0.5-s-long synthetic wavestreams contained enough information to identify the same trends as the conventional wavestreams for this application; thus, the use of synthetic wavestreams as a tool for selecting an appropriate wavestream recording length was demonstrated.

scholarly journals A variational Bayesian neural network for structural health monitoring and cost-informed decision-making in miter gates

2020 ◽  
pp. 147592172090454 ◽  
Author(s):  
Manuel A Vega ◽  
Michael D Todd
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Decision Making ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Informed Decision ◽  
Informed Decision Making ◽  
Bayesian Neural Network ◽  
Bayesian Neural Networks ◽  
Structural Health

Many physics-based and surrogate models used in structural health monitoring are affected by different sources of uncertainty such as model approximations and simplified assumptions. Optimal structural health monitoring and prognostics are only possible with uncertainty quantification that leads to an informed course of action. In this article, a Bayesian neural network using variational inference is applied to learn a damage feature from a high-fidelity finite element model. Bayesian neural networks can learn from small and noisy data sets and are more robust to overfitting than artificial neural networks, which make it very suitable for applications such as structural health monitoring. Also, uncertainty estimates obtained from a trained Bayesian neural network model are used to build a cost-informed decision-making process. To demonstrate the applicability of Bayesian neural networks, an example of this approach applied to miter gates is presented. In this example, a degradation model based on real inspection data is used to simulate the damage evolution.

Artificial Neural Networks for Structural Health Monitoring of Helicopter Harsh Landings

2013 ◽  
Vol 390 ◽  
pp. 192-197
Author(s):  
Giorgio Vallone ◽  
Claudio Sbarufatti ◽  
Andrea Manes ◽  
Marco Giglio
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Structural Damage ◽  
Numerical Models ◽  
Damage State ◽  
Operational Conditions ◽  
Structural Health ◽  
Artificial Neural

The aim of the current paper is to explore fuselage monitoring possibilities trough the usage of Artificial Neural Networks (ANNs), trained by the use of numerical models, during harsh landing events. A harsh landing condition is delimited between the usual operational conditions and a crash event. Helicopter structural damage due to harsh landings is generally less severe than damage caused by a crash but may lead to unscheduled maintenance events, involving costs and idle times. Structural Health Monitoring technologies, currently used in many application fields, aim at the continuous detection of damage that may arise, thereby improving safety and reducing maintenance idle times by the disposal of a ready diagnosis. A landing damage database can be obtained with relatively little effort by the usage of a numerical model. Simulated data are used to train various ANNs considering the landing parameter values as input. The influence of both the input and output noise on the system performances were taken into account. Obtained outputs are a general classification between damaged and undamaged conditions, based on a critical damage threshold, and the reconstruction of the fuselage damage state.

Application of neural networks for the structural health monitoring in curtain-wall systems

2007 ◽  
Vol 29 (12) ◽  
pp. 3475-3484 ◽  
Author(s):  
Ch. Efstathiades ◽  
C.C. Baniotopoulos ◽  
P. Nazarko ◽  
L. Ziemianski ◽  
G.E. Stavroulakis
Keyword(s):  
Neural Networks ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Curtain Wall ◽  
Structural Health
Sign in / Sign up

Export Citation Format

Share Document